LightGCNxGPT: integrating LightGCN with GPT for enhanced personalised recommendations and explainability in recommender systems

Recommendation systems have emerged as a pivotal tool in shaping our daily choices. Traditional systems face many challenges in providing users with accurate recommendations, especially when there is limited data. Furthermore, these systems fail to provide users with explanations for the recommendat...

Full description

Saved in:
Bibliographic Details
Main Author: Tiyyagura, Rochana
Other Authors: Liu Siyuan
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
GPT
LLM
Online Access:https://hdl.handle.net/10356/175242
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-175242
record_format dspace
spelling sg-ntu-dr.10356-1752422024-04-26T15:41:59Z LightGCNxGPT: integrating LightGCN with GPT for enhanced personalised recommendations and explainability in recommender systems Tiyyagura, Rochana Liu Siyuan School of Computer Science and Engineering SYLiu@ntu.edu.sg Computer and Information Science Large language models LightGCN GPT LLM Recommendation systems Graph convolutional network Recommendation systems have emerged as a pivotal tool in shaping our daily choices. Traditional systems face many challenges in providing users with accurate recommendations, especially when there is limited data. Furthermore, these systems fail to provide users with explanations for the recommendations made which is crucial in cultivating trust and transparency. In light of the recent focus on Large Language Models (LLMs), this work proposes a novel framework called LightGCNxGPT that improves recommender systems by employing effective methods such as neighbourhood aggregation and user and item refinement. The LLM based paradigm proposed leverages upon the power of GPT, a popular LLM, to enhance the recommendations made by the state-of-the-art LightGCN model through innovative techniques, namely (i) User Information Refinement (ii) Item Noise Filtering (iii) GPT-Based Explanation Generation. Furthermore, theoretical analysis is provided to support the rationale behind the work and chosen methodology. The experimental results evaluated on a benchmark dataset showcases that the LightGCNxGPT model demonstrates superior performance over current state-of-the-art models. Bachelor's degree 2024-04-23T00:58:53Z 2024-04-23T00:58:53Z 2024 Final Year Project (FYP) Tiyyagura, R. (2024). LightGCNxGPT: integrating LightGCN with GPT for enhanced personalised recommendations and explainability in recommender systems. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175242 https://hdl.handle.net/10356/175242 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
Large language models
LightGCN
GPT
LLM
Recommendation systems
Graph convolutional network
spellingShingle Computer and Information Science
Large language models
LightGCN
GPT
LLM
Recommendation systems
Graph convolutional network
Tiyyagura, Rochana
LightGCNxGPT: integrating LightGCN with GPT for enhanced personalised recommendations and explainability in recommender systems
description Recommendation systems have emerged as a pivotal tool in shaping our daily choices. Traditional systems face many challenges in providing users with accurate recommendations, especially when there is limited data. Furthermore, these systems fail to provide users with explanations for the recommendations made which is crucial in cultivating trust and transparency. In light of the recent focus on Large Language Models (LLMs), this work proposes a novel framework called LightGCNxGPT that improves recommender systems by employing effective methods such as neighbourhood aggregation and user and item refinement. The LLM based paradigm proposed leverages upon the power of GPT, a popular LLM, to enhance the recommendations made by the state-of-the-art LightGCN model through innovative techniques, namely (i) User Information Refinement (ii) Item Noise Filtering (iii) GPT-Based Explanation Generation. Furthermore, theoretical analysis is provided to support the rationale behind the work and chosen methodology. The experimental results evaluated on a benchmark dataset showcases that the LightGCNxGPT model demonstrates superior performance over current state-of-the-art models.
author2 Liu Siyuan
author_facet Liu Siyuan
Tiyyagura, Rochana
format Final Year Project
author Tiyyagura, Rochana
author_sort Tiyyagura, Rochana
title LightGCNxGPT: integrating LightGCN with GPT for enhanced personalised recommendations and explainability in recommender systems
title_short LightGCNxGPT: integrating LightGCN with GPT for enhanced personalised recommendations and explainability in recommender systems
title_full LightGCNxGPT: integrating LightGCN with GPT for enhanced personalised recommendations and explainability in recommender systems
title_fullStr LightGCNxGPT: integrating LightGCN with GPT for enhanced personalised recommendations and explainability in recommender systems
title_full_unstemmed LightGCNxGPT: integrating LightGCN with GPT for enhanced personalised recommendations and explainability in recommender systems
title_sort lightgcnxgpt: integrating lightgcn with gpt for enhanced personalised recommendations and explainability in recommender systems
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/175242
_version_ 1800916397442727936